스킬 mantis-meta-agent

📦

mantis-meta-agent

Name: mantis-meta-agent
Author: google

콘텐츠 리비전 r1 치명적 ⚙️ 외부 명령어📁 파일 시스템 접근

Coordinate Continuous Mantis Security Reviews

Long security reviews require coordinated specialist stages and reliable campaign state across repeated passes. This skill supervises Mantis subagents, preserves findings, and manages optional synchronization and snapshot provenance.

지원: Claude Codex Code(CC)

⚠️ 38 나쁨

Maintain this Skill? Claim it ⚠️ 38 나쁨

이 Skill을 자동으로 설치하지 마세요.

공식 정책에 따라 설치 작업 전에 운영자 검토가 필요합니다.

내 에이전트로 설치

이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.

에이전트 요청

Review the Skillstore skill "mantis-meta-agent" from https://skillstore.io/skills/google-mantis-meta-agent.md and its manifest at https://skillstore.io/api/skills/google-mantis-meta-agent/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.

에이전트가 읽기 쉬운 리소스

AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.

Markdown 상세 GET /skills/google-mantis-meta-agent.md 서명된 manifest GET /api/skills/google-mantis-meta-agent/manifest 서명된 lockfile GET /api/skills/google-mantis-meta-agent/lockfile

테스트해 보기

"mantis-meta-agent" 사용 중입니다. What should happen when an opt-in sync finds local repository changes?

예상 결과:

Illustrative status: synchronization skipped because local changes exist.
Preserve the current tree and report why synchronization did not run.
Attempt the requested snapshot only under the campaign's pinning rules.

"mantis-meta-agent" 사용 중입니다. What should a completed pass preserve for the next review?

예상 결과:

Expected archive contents: finding records, campaign state, and a copied knowledge base.
Expected live state: the knowledge base remains available and the pass counter advances.
Expected report: reproduced actionable findings, supporting evidence, and patch verification results.

"mantis-meta-agent" 사용 중입니다. The harness exposes no subagent execution logs. What should reflection receive?

예상 결과:

Expected delegation: provide an explicit empty log list and request a missing-transcript insight for each executed stage.

보안 감사

치명적

v1 • 2026. 10. 4. 버전별 보고서 열기

Most static findings are Markdown formatting, campaign state references, or legitimate repository checks, not shell execution or system reconnaissance. Confirmed concerns include unproven backup ownership and unredacted transcript access; semantic findings identify self-declared testing authorization and permissive snapshot verification. No evidence found of credential exfiltration, malware installation, or instructions to manipulate this marketplace audit.

스캔된 파일

612

분석된 줄 수

검토 항목

오탐 무시됨

확인된 보안 우려 사항 (2)

치명적

SKILL.md:111-120 SKILL.md:469-481

Prompt Injection Attempt Detected

The directive states, "You are authorized and encouraged to use whatever suitable tools are at your disposal," including testing live endpoints. This self-declared authorization can mislead agents into testing outside user-approved scope or running untrusted targets without isolation.

The text explicitly grants broad tool-use authorization and includes live endpoints, reproduction, and exploit-chain stages without defining permission or isolation boundaries. Defensive intent does not establish authorization.

중간

SKILL.md:293-303 SKILL.md:326-341

Snapshot Verification Accepts Incomplete or Writable Targets

Snapshot verification permits pinning when missing files are not already referenced and labels write protection as best effort. Downstream stages can treat an incomplete or still-writable target as pinned evidence.

The instructions explicitly permit skipped files and best-effort chmod before setting pinned status. This contradicts the claimed immutable, authoritative snapshot guarantee.

기능 검토 항목 (6)

이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.

중간

SKILL.md:173

Ruby/shell backtick execution

`find <target_root> -regextype posix-extended -regex '.*\.bak-[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0

The find command deletes UUID-shaped backups without requiring proof that Mantis created them. User-owned backups can match despite lock and state-directory exclusions.

중간

SKILL.md:182

Ruby/shell backtick execution

invisible to every dirty check. Delete stray `mantis-summary.md` and

Pre-sync cleanup deletes mantis-summary.md by filename before checking repository changes. A user-owned or modified file with that name can be lost.

중간

SKILL.md:183

Ruby/shell backtick execution

UUID-shaped `*.bak-<uuid>` files at the LIVE root first (same narrow

Cleanup deletes UUID-shaped backups at the live root based on their names. The instructions do not require provenance proving these files are disposable.

중간

SKILL.md:184

Ruby/shell backtick execution

glob as the SCOPE rule above — never the broad `*.bak-*` glob for

The narrow glob reduces accidental matches but still permits deleting user-owned UUID-shaped backups. Filename shape alone does not establish Mantis ownership.

중간

SKILL.md:173

Hidden file access

`find <target_root> -regextype posix-extended -regex '.*\.bak-[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0

The find command deletes UUID-shaped backups without requiring proof that Mantis created them. User-owned backups can match despite lock and state-directory exclusions.

중간

SKILL.md:498

Hidden file access

`<appDataDir>/brain/<conversation_id>/.system_generated/logs/transcript.jsonl`,

The reflection stage receives full campaign execution transcripts from harness-private storage without mandatory redaction. Logs can contain credentials or private context beyond needed learning summaries.

위험 요인

⚙️ 외부 명령어 (50)

📁 파일 시스템 접근 (27)

감사자: codex

이 보고서 공유 및 인용

버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.

버전별 보고서 열기

보고서 링크 복사

https://skillstore.io/skills/google-mantis-meta-agent/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 배지

[![Skillstore security assessment](https://skillstore.io/badges/skills/google-mantis-meta-agent/security.svg)](https://skillstore.io/skills/google-mantis-meta-agent?utm_source=security_passport_badge)

HTML 배지

<a href="https://skillstore.io/skills/google-mantis-meta-agent?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/google-mantis-meta-agent/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

임베드 카드

<iframe src="https://skillstore.io/embed/skills/google-mantis-meta-agent.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

학술 인용 (APA · BibTeX · CFF)

APA 인용

google. (2026). mantis-meta-agent security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/google-mantis-meta-agent/audits/1

BibTeX 인용

@techreport{google-google-mantis-meta-agent-2026,
  author = {google},
  title = {mantis-meta-agent security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/google-mantis-meta-agent/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "mantis-meta-agent security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "google"
date-released: "2026-10-04"
url: "https://skillstore.io/skills/google-mantis-meta-agent/audits/1"
identifiers:
  - type: other
    value: "skillstore:google-mantis-meta-agent:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 점수

이 점수의 이유 증거 신뢰도: 낮음

아키텍처

유지보수성

콘텐츠

커뮤니티

사양 준수

만들 수 있는 것

Coordinate a Repository Review

Supervise specialist review stages and preserve validated findings across repeated passes on an explicitly authorized repository.

Track Review Provenance

Use optional synchronization, pass snapshots, and archives to compare campaign results across repository revisions.

Supervise an Artifact Campaign

Coordinate appropriate analysis specialists for an authorized binary or firmware artifact in an isolated testing environment.

이 프롬프트를 사용해 보세요

Inspect Campaign Readiness

Inspect readiness for a Mantis campaign on [authorized repository]. List missing subagents, tools, and state inputs. Do not start testing or modify files.

Supervise a Bounded Review

Supervise one Mantis pass on [authorized repository] using [external state directory]. Do not sync. Stop after archiving and summarize reproduced findings.

Request a Synchronized Pass

Run one authorized Mantis pass with --sync and --state_root=[external directory]. Preserve local changes and unknown artifacts. Halt if snapshot completeness or protection fails.

Resume and Steer a Campaign

Resume [authorized campaign] from its existing state. Check snapshot provenance and archive integrity. Focus the next pass on [component]. Require consent before sensitive-log processing.

모범 사례

Define authorized targets, permitted testing methods, and stopping conditions before launching a campaign.
Keep campaign state outside the target tree, preserve unknown artifacts, and verify snapshot completeness before trusting provenance.
Use isolated reproduction environments and redact sensitive campaign transcripts before sharing them with reflection subagents.

피하기

Treating the skill's authorization statement as permission to test arbitrary endpoints or execute untrusted binaries.
Deleting files solely because their names resemble generated Mantis artifacts.
Treating unpinned, incomplete, or writable snapshots as immutable evidence for authoritative findings.

자주 묻는 질문

Which AI tools are listed as supported?

The metadata lists Claude, Codex, and Claude Code. Actual execution requires a harness with compatible Mantis subagents and delegation tools.

Does this package include the complete review pipeline?

No. The reviewed package contains one instruction file. Specialist subagents, schemas, and supporting tools must be available separately.

Does the supervisor patch vulnerabilities directly?

No. It delegates patching and reproduction to specialist subagents and coordinates their results.

Does synchronization run automatically?

No. Synchronization and pinning require --sync or an explicit request. Default passes operate against the live target.

Can a campaign resume after interruption?

The instructions define pass recovery and snapshot reuse checks. Missing previously pinned snapshots should stop the campaign rather than silently replace evidence.

What safeguards are needed before use?

Confirm testing authorization, isolate untrusted execution, verify artifact ownership before deletion, redact transcripts, and require complete protected snapshots.

개발자 세부 정보

작성자

google

라이선스

MIT

Skillstore 리비전

버전 안내

작성자가 버전을 선언하지 않았습니다.

리포지토리

https://github.com/google/mantis/tree/f48a85e8823ee6f4824ae9a24b9b2efb8aab8c9a/mantis-meta-agent

참조

44cf00a7ced88385654599ad1ed145fec23ee8ed

유지보수 최신성

2026. 10. 5.

사용량

0 다운로드 · 0 조회

파일 구조

📄 SKILL.md